Predicting Energy Consumption in Residential Buildings Using Advanced Machine Learning Algorithms

The share of residential building energy consumption in global energy consumption has rapidly increased after the COVID-19 crisis. The accurate prediction of energy consumption under different indoor and outdoor conditions is an essential step towards improving energy efficiency and reducing carbon footprints in the residential building sector. In this paper, a PSO-optimized random forest classification algorithm is proposed to identify the most important factors contributing to residential heating energy consumption. A self-organizing map (SOM) approach is applied for feature dimensionality reduction, and an ensemble classification model based on the stacking method is trained on the dimensionality-reduced data. The results show that the stacking model outperforms the other models with an accuracy of 95.4% in energy consumption prediction. Finally, a causal inference method is introduced in addition to Shapley Additive Explanation (SHAP) to explore and analyze the factors influencing energy consumption. A clear causal relationship between water pipe temperature changes, air temperature, and building energy consumption is found, compensating for the neglect of temperature in the SHAP analysis. The findings of this research can help residential building owners/managers make more informed decisions around the selection of efficient heating management systems to save on energy bills.

Automated summary

The share of residential building energy consumption in global energy consumption has rapidly increased after the COVID-19 crisis. Accurate prediction of energy consumption under different indoor and outdoor conditions is crucial for improving energy efficiency and reducing carbon footprints in the residential building sector. This paper proposes a PSO-optimized random forest classification algorithm to identify the key factors contributing to residential heating energy consumption. A self-organizing map (SOM) approach is used for feature dimensionality reduction, and an ensemble classification model based on the stacking method is trained on the reduced data. The stacking model outperforms other models with a 95.4% accuracy in energy consumption prediction. The research findings show a causal relationship between water pipe temperature changes, air temperature, and building energy consumption, providing valuable insights for residential building owners/managers in selecting efficient heating management systems to save on energy bills.